> For the complete documentation index, see [llms.txt](https://docs.allganize.ai/alli-llm-app-market/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.allganize.ai/alli-llm-app-market/manual/for_admin/default-apps/marketing/pop_text_creation.md).

# 商品画像からPOP用の文章生成

商品画像からPOP用の文章生成アプリでは、商品の画像から、POPで利用する文章案を生成します。

## フローの全体図 <a href="#overall" id="overall"></a>

<figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2FmyPt82HtjTL1X3O6ZsRf%2Fimage.png?alt=media&amp;token=3d272a1d-a2a0-42d9-8a90-c9458728ccf0" alt=""><figcaption></figcaption></figure>

## 概要 <a href="#outline" id="outline"></a>

商品画像からPOP用の文章生成アプリは、アップロードする画像データ(jpegやpingデータ)から、LLM実行ノードで商品のPOP文章を作成します。

### POPの文章を作成したい画像をアップロードする(LLMインプットノード) <a href="#llm-input-node" id="llm-input-node"></a>

LLMインプットノードで画像データをアップロードし変数に保存します。

* 選択タブ：アップロード
* 変数：＠PICTURE

  * 変数種別：会話変数
  * タイプ：ドキュメント

  <div><figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2FqM6Or7Tl41nLvGLHo0ri%2Fimage.png?alt=media&amp;token=7023a5c4-353b-4d40-b1bb-c3b7cb25875b" alt=""><figcaption></figcaption></figure> <figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2Ff7gFyfyXTeli9nMUfCFm%2Fimage.png?alt=media&amp;token=cf3b584f-3bf8-45fb-a2d8-391f85185437" alt=""><figcaption></figcaption></figure></div>

### アップロードされた画像データからPOP文章を作成(LLM実行ノード) <a href="#llm-node" id="llm-node"></a>

LLM実行ノードでは、アップロードした画像データを保存した変数(＠PICTURE)をプロンプトで指定し、LLMがPOP文章案の作成を行います。

* ベースモデル：GPT-4\_TURBO\_VISION
* プロンプト：商品画像からPOP文言を考える

<div><figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2FJqXKxH8E1YWGJqLFGbh6%2Fimage.png?alt=media&amp;token=53e38068-8861-425a-a139-838bfd398992" alt=""><figcaption></figcaption></figure> <figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2F9YrqxEBDY1cqgBnqqd3K%2Fimage.png?alt=media&amp;token=e4381b23-ca0d-40e5-9bf8-405db2e48159" alt=""><figcaption></figcaption></figure></div>

<figure><img src="https://3244404108-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FR2CRA2CisD1pVQUgqd1g%2Fuploads%2FNsdk5VSmmWXedtbGMp1V%2Fimage.png?alt=media&amp;token=1d16df82-b164-4e02-9f94-caa7fc98978a" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.allganize.ai/alli-llm-app-market/manual/for_admin/default-apps/marketing/pop_text_creation.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
